linux-kernel - Re: [PATCH v7 13/13] arm64: topology: divorce MC scheduling domain from core

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 14 Mar 2018 12:43:02 +0000
From:   Morten Rasmussen <morten.rasmussen@....com>
To:     Brice Goglin <brice.goglin@...il.com>
Cc:     Jeremy Linton <jeremy.linton@....com>, mark.rutland@....com,
        vkilari@...eaurora.org, lorenzo.pieralisi@....com,
        catalin.marinas@....com, tnowicki@...iumnetworks.com,
        gregkh@...uxfoundation.org, will.deacon@....com,
        dietmar.eggemann@....com, rjw@...ysocki.net,
        linux-kernel@...r.kernel.org, ahs3@...hat.com,
        linux-acpi@...r.kernel.org, palmer@...ive.com,
        hanjun.guo@...aro.org, sudeep.holla@....com,
        austinwc@...eaurora.org, linux-riscv@...ts.infradead.org,
        john.garry@...wei.com, wangxiongfeng2@...wei.com,
        linux-arm-kernel@...ts.infradead.org, lenb@...nel.org
Subject: Re: [PATCH v7 13/13] arm64: topology: divorce MC scheduling domain
 from core_siblings

On Thu, Mar 08, 2018 at 09:41:17PM +0100, Brice Goglin wrote:
> 
> > Is there a good reason for diverging instead of adjusting the
> > core_sibling mask? On x86 the core_siblings mask is defined by the last
> > level cache span so they don't have this issue. 
> 
> No. core_siblings is defined as the list of cores that have the same
> physical_package_id (see the doc of sysfs topology files), and LLC can
> be smaller than that.
> Example with E5v3 with cluster-on-die (two L3 per package, core_siblings
> is twice larger than L3 cpumap):
> https://www.open-mpi.org/projects/hwloc/lstopo/images/2XeonE5v3.v1.11.png
> On AMD EPYC, you even have up to 8 LLC per package.

Right, I missed the fact that x86 reports a different cpumask for
topology_core_cpumask() which defines the core_siblings exported through
sysfs than the mask used to define MC level in the scheduler topology.
The sysfs core_siblings is defined by the package_id, while the MC level
is defined by the LLC.

Thanks for pointing this out.

On arm64 MC level and sysfs core_siblings are currently defined using
the same mask, but we can't break sysfs, so using different masks is the
only option.

Morten